Commit graph

33 commits

Author SHA1 Message Date
Krish Dholakia
5f993f46a0 anthropic prompt caching cost tracking (#5453)
* fix(utils.py): support 'drop_params' for embedding requests

Fixes https://github.com/BerriAI/litellm/issues/5444

* feat(anthropic/cost_calculation.py): Support calculating cost for prompt caching on anthropic

* feat(types/utils.py): allows us to migrate to openai's equivalent, once that comes out

* fix: fix linting errors

* test: mark flaky test
2024-08-31 14:09:35 -07:00
Krrish Dholakia
cf1a1605a6 feat(cost_calculator.py): only override base model if custom pricing is set 2024-08-19 16:05:49 -07:00
Krish Dholakia
c7627a7de6 Merge pull request #5219 from dhlidongming/fix-messages-length-check
Fix incorrect message length check in cost calculator
2024-08-17 14:01:59 -07:00
Krrish Dholakia
29bedae79f feat(google_ai_studio_endpoints.py): support pass-through endpoint for all google ai studio requests
New Feature
2024-08-17 10:46:59 -07:00
Krrish Dholakia
9609505d0c fix(litellm_logging.py): fix price information logging to s3 2024-08-16 16:42:38 -07:00
Krrish Dholakia
ef51f8600d feat(litellm_logging.py): support logging model price information to s3 logs 2024-08-16 16:21:34 -07:00
lidongming
47c3b6eca9 Fix incorrect message length check in cost calculator 2024-08-15 16:59:38 +08:00
Krrish Dholakia
a9168df113 fix(cost_calculator.py): fix cost calc 2024-08-12 16:47:15 -07:00
Krrish Dholakia
40b86e7d07 fix(cost_calculator.py): handle openai usage pydantic object
Fixes https://github.com/BerriAI/litellm/issues/5165
2024-08-12 15:45:21 -07:00
Krrish Dholakia
6f7d051261 fix(cost_calculator.py): respect litellm.suppress_debug_info for cost calc
Fixes https://github.com/BerriAI/litellm/issues/4818#issuecomment-2263795765
2024-08-01 12:27:09 -07:00
Krrish Dholakia
0bcfdafc58 fix(utils.py): fix model registeration to model cost map
Fixes https://github.com/BerriAI/litellm/issues/4972
2024-07-30 18:15:00 -07:00
Krrish Dholakia
a6b053f535 feat(databricks.py): support vertex mistral cost tracking 2024-07-27 20:22:35 -07:00
Krrish Dholakia
4687b12732 fix(litellm_logging.py): log response_cost=0 for failed calls
Fixes https://github.com/BerriAI/litellm/issues/4604
2024-07-15 19:25:56 -07:00
Krrish Dholakia
3f965df68b fix(llm_cost_calc/google.py): fix google embedding cost calculation
Fixes https://github.com/BerriAI/litellm/issues/4630
2024-07-11 11:55:48 -07:00
Krish Dholakia
ece24015cc Merge branch 'main' into litellm_tts_pricing 2024-07-06 14:57:34 -07:00
Krrish Dholakia
1390447966 fix(cost_calculator.py): fix completion_response check 2024-07-06 12:28:46 -07:00
Krrish Dholakia
356c18c929 feat(litellm_logging.py): support cost tracking for tts calls 2024-07-05 22:09:08 -07:00
Krrish Dholakia
6220b70261 fix(cost_calculator.py): support openai+azure tts calls 2024-07-05 20:58:08 -07:00
Krrish Dholakia
97ad7eb535 fix(cost_calculator.py): handle unexpected error in cost_calculator.py 2024-06-28 14:53:00 -07:00
Krish Dholakia
fa1cb7d903 Merge branch 'main' into litellm_response_cost_headers 2024-06-27 21:33:09 -07:00
Krrish Dholakia
e81fa6ecad fix(cost_calculator.py): infer provider name if not given
Fixes https://github.com/BerriAI/litellm/issues/4452
2024-06-27 18:41:04 -07:00
Krrish Dholakia
be5d918211 fix(utils.py): return 'response_cost' in completion call
Closes https://github.com/BerriAI/litellm/issues/4335
2024-06-26 17:55:57 -07:00
spdustin@gmail.com
16c5ebfe25 fix: use per-token costs for claude via vertex_ai 2024-06-21 11:21:36 -05:00
Krish Dholakia
63277d4b7a Merge pull request #4295 from BerriAI/litellm_gemini_pricing_2
Vertex AI - character based cost calculation
2024-06-19 19:17:09 -07:00
Krrish Dholakia
edfe550165 feat(llm_cost_calc/google.py): do character based cost calculation for vertex ai
Calculate cost for vertex ai responses using characters in query/response

 Closes https://github.com/BerriAI/litellm/issues/4165
2024-06-19 17:18:42 -07:00
Ishaan Jaff
e9e0e85e39 fix add cost tracking for ft:gpt-4o-2024-05-1 2024-06-19 16:59:06 -07:00
Krrish Dholakia
21878d9ee7 fix(cost_calculator.py): fix time import 2024-06-17 20:27:18 -07:00
Krrish Dholakia
4fd054f188 feat(cost_calculator.py): add cost calculating for dynamic context window (vertex ai / google ai studio) 2024-06-17 12:38:10 -07:00
Krrish Dholakia
9d7f5d503c refactor(utils.py): refactor Logging to it's own class. Cut down utils.py to <10k lines.
Easier debugging

 Reference: https://github.com/BerriAI/litellm/issues/4206
2024-06-15 10:57:20 -07:00
Ishaan Jaff
90e297d745 fix azure cost tracking 2024-06-10 21:09:55 -07:00
Krrish Dholakia
2af3c43360 build(model_prices_and_context_window.json): update together ai model pricing - account for new categories 2024-06-08 19:56:35 -07:00
Krrish Dholakia
0a886eed6a fix(cost_calculator.py): fixes tgai unmapped model pricing
Fixes error where tgai helper function returned None. Enforces stronger type hints, refactors code, adds more unit testing.
2024-06-08 19:43:57 -07:00
Krrish Dholakia
7432c6a4d9 fix(utils.py): fix cost calculation for openai-compatible streaming object 2024-06-04 10:36:25 -07:00